Comparative Analysis of Backpropagation With Learning Vector Quantization (LVQ) to Predict Rainfall in Medan City

Rainfall is a very important factor in agriculture and development planning. This study aims to predict rainfall and rainfall properties in Medan using a multilayer neural network with Backpropagation and Learning Vector Quantization (LVQ) algorithms. Rainfall data used for training is rainfall data for the last 30 years. The parameters used in this study consisted of two inputs namely the month and the volume of rainfall. The training process produces the best architecture with 3 layer three for Backpropagation and two layers for Learning Vector Quantization with learning rate 0.5. From the prediction results obtained Backpropagation algorithm more accurate in predicting rainfall data last 30 years compared with LVQ with an average difference of 21.99%. Backpropagation and LVQ algorithms have better accuracy in the dry season, with accuracy for Backpropagation algorithm between 75 - 99% and LVQ algorithm of 60 - 82%. For both algorithms, the influence of El-Nino and La-Nina phenomena is not so significant.